# cell type annotations
display_df(cell_df_complete)

# organ annotations
display_df(organ_df_complete)

# stage annotations
display_df(stage_df_complete)

experiment_id = "ERP132587"

path_to_create_exp_script = "/Users/scarsana/Desktop/git/scRNA-Seq/scripts/Create_ExpLib_tables.py" 
path_to_barcodes_script = "/Users/scarsana/Desktop/git/scRNA-Seq/scripts/create_scRNASeq_barcode_v2.py"
experiment_type = "scRNA"

path_to_output_main = "/Users/scarsana/Desktop/git/expression-annotations/Notebooks/scRNA/" 
path_to_output = "{}{}/".format(path_to_output_main, experiment_id)
library_path_from_script = "{}scRNASeqLibrary_{}.tsv".format(path_to_output, experiment_id)
experiment_path_from_script = "{}scRNASeqExperiment_{}.tsv".format(path_to_output, experiment_id)
barcode_path = "{}scRNASeq_barcode_{}.tsv".format(path_to_output, experiment_id)
barcode_to_add_path = "{}complete_scRNASeq_barcode_{}.tsv".format(path_to_output, experiment_id)
library_to_add_path = "{}complete_scRNASeqLibrary_{}.tsv".format(path_to_output, experiment_id)
experiment_to_add_path = "{}complete_RNASeqExperiment_{}.tsv".format(path_to_output, experiment_id)
script_file = "{}.ipynb".format(experiment_id)
commit_message_exp = '"adding annotated scRNA experiment {}"'.format(experiment_id)
commit_message_py = '"adding annotation files for {} to notebook folder"'.format(experiment_id)



## to add to git
path_to_git_annotations = "/Users/scarsana/Desktop/git/expression-annotations/scRNA_Seq/"
git_library_path = "{}scRNASeqLibrary_merged.tsv".format(path_to_git_annotations)
git_experiment_path = "{}scRNASeqExperiment.tsv".format(path_to_git_annotations)
git_barcode_path = "{}scRNASeq_barcode_{}.tsv".format(path_to_git_annotations, experiment_id)

## columns
library_cols = ['#libraryId', 'experimentId', 'platform', 'SRSId', 'anatId', 'anatName', 'cellTypeId', 'cellTypeName', 'stageId', 'stageName', 'url_GSM', 'infoOrgan', 'infoCellType_abInitio', 'infoCellType_inferred', 'clusterId', 'clusterName', 'infoStage', 'anatAnnotationStatus', 'cellTypeAnnotationStatus', 'stageAnnotationStatus', 'sex', 'strain', 'genotype', 'speciesId', 'RNAseqTags', 'protocol', 'protocolType', 'lib_name', 'sampleName', 'comment', 'condition', 'annotatorId', 'lastModificationDate']
barcode_cols = ['barcode', 'cluster', 'library', 'experiment', 'tissue', 'cell_type', 'anatId_a_posteriori', 'anatName_a_posteriori', 'anat_a_posteriori_annotationStatus', 'cellTypeId', 'cellTypeName', 'cellTypeAnnotationStatus', 'name_Library', 'comments']

## annotation sheet paths (maybe make these into their own folder)
annotation_files_path = "{}annotation_files/".format(path_to_output)
import os
if not os.path.exists(annotation_files_path):
    os.makedirs(annotation_files_path)

info_anat_path = "{}info_anat.tsv".format(annotation_files_path)
info_anat_complete_path = "{}info_anat_complete.tsv".format(annotation_files_path)
info_stage_path = "{}info_dev_stage.tsv".format(annotation_files_path)
info_stage_complete_path = "{}info_dev_stage_complete.tsv".format(annotation_files_path)
info_celltype_path = "{}info_celltype.tsv".format(annotation_files_path)
info_celltype_complete_path = "{}info_celltype_complete.tsv".format(annotation_files_path)

## barcode file & matching library names - 10X only
path_to_barcode_file = "{}barcode_{}.csv".format(path_to_output, experiment_id)
lib_names_path = "{}matching_lib_names_{}.tsv".format(path_to_output, experiment_id)

import warnings
warnings.simplefilter(action='ignore', category=FutureWarning)
import pandas as pd
import numpy as np
from IPython.display import display, HTML
import csv
import scanpy as sc

# displays df with the scrollbar next to the DataFrame
def display_df(df):
    pd.set_option("display.max_rows", None)
    pd.set_option("display.max_columns", None)
    display(HTML("<div style='height: 200px; overflow: auto; width: fit-content'>" +
        df.style.to_html(index=False) + "</div>"))

# function that compares two columns in a dataframe and tells you which ones are not equal (case insensitive)
def compare_columns(df, col1, col2, return_col):
    compare_return = df[col1].str.lower() != df[col2].str.lower()  
    df.loc[compare_return, return_col] 
    if not any(compare_return):
        print("The two columns are equal (case insensitive)")
    else:
        print("The following rows are not equal: ")
        print(df.loc[compare_return, [return_col, col1, col2]])

# fixes formatting of file to match libreoffice settings/historic file format
def update_format(path):
    with open(path, 'r') as file:
        filedata = file.read()
    # Replace the target string
    filedata = filedata.replace("\t\"\"", "\t")
    # Write the file out again
    with open(path, 'w') as file:
        file.write(filedata)

# checks for duplicate values in a specific column and prints those values + the corresponding library id
def dup_check(df, column):
    duplicateCheck = df.duplicated(subset=[column], keep=False)
    duplicateCheck.sort_values(inplace=True)
    if duplicateCheck.unique().any() == False:
        print("no duplicate values in " + column)
    elif duplicateCheck.unique().any() == True and column != '#libraryId':
        dups = df[duplicateCheck].loc[:,['#libraryId', column]]
        df_dups = pd.DataFrame(dups)
        df_dups.sort_values(inplace=True, by=column)
        print(df_dups)
    elif duplicateCheck.unique().any() == True and column == '#libraryId':
        print(df[duplicateCheck].loc[:,['#libraryId']])

# prints all unique values in a specific column
def unique_sorted(df, column):
    unique = df[column].unique()
    unique.sort()
    print(unique)

/var/folders/b5/crkp117d43q5mcndnwlrww3w0000gn/T/ipykernel_81515/2872653486.py:3: DeprecationWarning: 
Pyarrow will become a required dependency of pandas in the next major release of pandas (pandas 3.0),
(to allow more performant data types, such as the Arrow string type, and better interoperability with other libraries)
but was not found to be installed on your system.
If this would cause problems for you,
please provide us feedback at https://github.com/pandas-dev/pandas/issues/54466
        
  import pandas as pd

! python3 $path_to_create_exp_script $experiment_id $path_to_output $experiment_type

/Users/scarsana/Desktop/git/scRNA-Seq/scripts/Create_ExpLib_tables.py:97: SyntaxWarning: invalid escape sequence '\('
  all_protoc = [w.replace('(', '\(') for w in all_protoc]
/Users/scarsana/Desktop/git/scRNA-Seq/scripts/Create_ExpLib_tables.py:98: SyntaxWarning: invalid escape sequence '\)'
  all_protoc = [w.replace(')', '\)') for w in all_protoc] 
/Users/scarsana/Desktop/git/scRNA-Seq/scripts/Create_ExpLib_tables.py:11: DeprecationWarning: 
Pyarrow will become a required dependency of pandas in the next major release of pandas (pandas 3.0),
(to allow more performant data types, such as the Arrow string type, and better interoperability with other libraries)
but was not found to be installed on your system.
If this would cause problems for you,
please provide us feedback at https://github.com/pandas-dev/pandas/issues/54466
        
  import pandas as pd
Be patient, it may take a few minutes.
E-MTAB-11067
0it [00:00, ?it/s]
0 samples dont have attributes, try to find them somewhere else
0it [00:00, ?it/s]
0 samples dont have attributes

library = pd.read_csv(library_path_from_script, sep='\t', index_col=False, keep_default_na=False, na_values=['NULL','null', 'nan','NaN', " "], dtype=object)
display_df(library)

infoOrgan = library['infoOrgan'].drop_duplicates().sort_values()
organ_df = pd.DataFrame(infoOrgan)
organ_df = organ_df.reindex(columns=[*organ_df.columns.tolist(), 'notes_anat', 'anatId_', 'anatName_', 'anatAnnotationStatus_', 'infoOrgan_new', 'comment_anat'], fill_value="")
organ_df.to_csv(info_anat_path, sep="\t", index=False, quoting=csv.QUOTE_ALL)
if not os.path.exists(info_anat_complete_path): 
    organ_df.to_csv(info_anat_complete_path, sep="\t", index=False, quoting=csv.QUOTE_ALL)

# options for anatAnnotationStatus: perfect match, missing child term, other

organ_df_complete = pd.read_csv(info_anat_complete_path, sep='\t', index_col=False, keep_default_na=False, na_values=['NULL','null', 'nan','NaN', " "], dtype=object)
display_df(organ_df_complete)

library = library.merge(organ_df_complete, left_on='infoOrgan', right_on='infoOrgan')

library['anatId'] = library['anatId_'].values
library['anatName'] = library['anatName_'].values
library['anatAnnotationStatus'] = library['anatAnnotationStatus_'].values

## optional - update infoOrgan, add anat-specific comments 
#library['infoOrgan'] = library['infoOrgan_new'].values
#library['comment'] = library[['comment', 'comment_anat']].agg(' '.join, axis=1)

# reformat, save progress
library = library[library_cols]
display_df(library)
library.to_csv(library_to_add_path, sep="\t", index=False, quoting=csv.QUOTE_ALL)

infoStage = library['infoStage'].drop_duplicates().sort_values()
stage_df = pd.DataFrame(infoStage)
stage_df = stage_df.reindex(columns=[*stage_df.columns.tolist(), 'notes_stage', 'stageId_', 'stageName_', 'stageAnnotationStatus_', 'infoStage_new','comment_stage'], fill_value="")
stage_df.to_csv(info_stage_path, sep="\t", index=False, quoting=csv.QUOTE_ALL)
if not os.path.exists(info_stage_complete_path): 
    stage_df.to_csv(info_stage_complete_path, sep="\t", index=False, quoting=csv.QUOTE_ALL)

# options for stageAnnotationStatus: perfect match, missing child term, other

stage_df_complete = pd.read_csv(info_stage_complete_path, sep='\t', index_col=False, keep_default_na=False, na_values=['NULL','null', 'nan','NaN', " "], dtype=object)
display_df(stage_df_complete)

library = library.merge(stage_df_complete, left_on='infoStage', right_on='infoStage')

library['stageId'] = library['stageId_'].values
library['stageName'] = library['stageName_'].values
library['stageAnnotationStatus'] = library['stageAnnotationStatus_'].values

## optional - update infoOrgan, add anat-specific comments 
#library['infoStage'] = library['infoStage_new'].values
#library['comment'] = library[['comment', 'comment_stage']].agg(' '.join, axis=1)

# reformat, save progress
library = library[library_cols]
display_df(library)
library.to_csv(library_to_add_path, sep="\t", index=False, quoting=csv.QUOTE_ALL)

#library.loc[library["sex"] == "male", "sex"] = "M"
#library.loc[library["sex"] == "female", "sex"] = "F"

#library.loc[:,'strain'] = ''

#library.loc[:,'genotype'] = ''

#library.loc[:,'speciesId'] = ''

# view
display_df(library)

# making these variables because we use them again in the experiment file
# usually 10X Genomics V1/V2/V3/V3.1, Smart-seq, Smart-seq2
my_protocol = '10X Genomics V2'
# Full-length or 3'end or 5'end
my_protocolType = "3'end"

library.loc[:,'protocol'] = my_protocol
library.loc[:,'protocolType'] = my_protocolType
# scRNA-seq, Sn-scRNA-seq
library.loc[:,'RNAseqTags'] = 'Sn-scRNA-seq'

# view
display_df(library)

# ex. control, diet, light, reproductive capacity, time post mortem, time post feeding, 
# exercise details, menstruation, personality, litter size 
#library.loc[library["condition"] == "old", "condition"] = "new"

# view
display_df(library)

library.loc[:,'annotatorId'] = 'SAC'
library.loc[:,'lastModificationDate'] = '2025-01-28'

# view
display_df(library)

#library.loc[:,'comment'] = ''

library_file_complete = library[library_cols]

library_file_complete.to_csv(library_to_add_path, sep="\t", index=False, quoting=csv.QUOTE_ALL)

# view
display_df(library_file_complete)

barcode_column = "barcode"
library_column = "library"
cell_type_column = "CELL_TYPE"

! python3 $path_to_barcodes_script $path_to_output --scRNASeqLibrary $library_to_add_path --barcode_file $path_to_barcode_file --barcode_col $barcode_column --libName_col $library_column --cellType_col $cell_type_column --ignore_check --no_additional_file

/Users/scarsana/Desktop/git/scRNA-Seq/scripts/create_scRNASeq_barcode_v2.py:10: DeprecationWarning: 
Pyarrow will become a required dependency of pandas in the next major release of pandas (pandas 3.0),
(to allow more performant data types, such as the Arrow string type, and better interoperability with other libraries)
but was not found to be installed on your system.
If this would cause problems for you,
please provide us feedback at https://github.com/pandas-dev/pandas/issues/54466
        
  import pandas as pd
There are 2 unique libraries in scRNASeqLibrary.tsv table
There are 2 unique libraries in the barcode table provided
Be extra careful if not same number of libraries in both tables, always manually check the matching names in 'matching_lib_names.tsv' table output
100%|██████████████████████████████████████████| 2/2 [00:00<00:00, 21788.59it/s]
     name_Library new_lib_name
4091        SN224        SN224
5577        SN219        SN219
396         SN219        SN219
7036        SN219        SN219
9513        SN219        SN219
6658        SN219        SN219
2823        SN224        SN224
1932        SN219        SN219
6254        SN224        SN224
3371        SN224        SN224
9292        SN219        SN219
9509        SN219        SN219
2201        SN219        SN219
4148        SN224        SN224
6972        SN224        SN224
2579        SN219        SN219
5622        SN224        SN224
1527        SN219        SN219
5404        SN219        SN219
1040        SN219        SN219
0 libraries dont have any barcodes !!
the following libraries don't have any barcodes: set()

lib_names = pd.read_csv(lib_names_path, sep='\t', index_col=False, keep_default_na=False, na_values=['NULL','null', 'nan','NaN', " "], dtype=object)
display_df(lib_names)

barcode_file = pd.read_csv(barcode_path, sep='\t', index_col=False, keep_default_na=False, na_values=['NULL','null', 'nan','NaN', " "], dtype=object)

cell_type = barcode_file['cell_type'].drop_duplicates().sort_values()
cell_df = pd.DataFrame(cell_type)
cell_df = cell_df.reindex(columns=[*cell_df.columns.tolist(), 'notes_cell', 'cellTypeId_', 'cellTypeName_', 'cellTypeAnnotationStatus_', 'cell_type_new','comment_cell'], fill_value="")
cell_df.to_csv(info_celltype_path, sep="\t", index=False)
if not os.path.exists(info_celltype_complete_path): 
    cell_df.to_csv(info_celltype_complete_path, sep="\t", index=False)

# options for cellTypeAnnotationStatus: perfect match, missing child term, other

cell_df_complete = pd.read_csv(info_celltype_complete_path, sep='\t', index_col=False, keep_default_na=False, na_values=['NULL','null', 'nan','NaN', " "], dtype=object)
display_df(cell_df_complete)

barcode_file = barcode_file.merge(cell_df_complete, left_on='cell_type', right_on='cell_type')

barcode_file['cellTypeId'] = barcode_file['cellTypeId_'].values
barcode_file['cellTypeName'] = barcode_file['cellTypeName_'].values
barcode_file['cellTypeAnnotationStatus'] = barcode_file['cellTypeAnnotationStatus_'].values

# optional - update cell type name and add comments
barcode_file['cell_type'] = barcode_file['cell_type_new'].values
#barcode_file['comment'] = barcode_file[['comment', 'comment_cell']].agg(' '.join, axis=1)

barcode_file_complete = barcode_file[barcode_cols]
display_df(barcode_file_complete)
barcode_file_complete.to_csv(barcode_to_add_path, sep="\t", index=False, quoting=csv.QUOTE_ALL)

experiment = pd.read_csv(experiment_path_from_script, sep='\t', index_col=False, keep_default_na=False, na_values=['NULL','null', 'nan','NaN', " "], dtype=object)
experiment.head()

library_to_add = pd.read_csv(library_to_add_path, sep='\t', index_col=False, keep_default_na=False, na_values=['NULL','null', 'nan','NaN', " "], dtype=object)

# this will give you the number of rows in the complete library file 
# this should be the number of annotated libraries
ann_lib = len(library_to_add.index)
len(library_to_add.index)

2

# partial or total
experiment.loc[:,'experimentStatus'] = 'total'
# scRNA-seq, Sn-scRNA-seq for both we put: 'Sn-scRNA-seq, scRNA-seq'
experiment.loc[:,'RNAseqTags'] = 'Sn-scRNA-seq'


# see above cell, also can add as free text
experiment.loc[:,'numberOfAnnotatedLibraries'] = ann_lib

# these variables should already exist from above but if not can just add as free text
experiment.loc[:,'protocol'] = my_protocol
experiment.loc[:,'protocolType'] = my_protocolType

experiment.head()

#experiment.loc[:,'GSE'] = ''
#experiment.loc[:,'Bioproject'] = '' 
experiment.loc[:,'PMID'] = '36544022'
experiment.loc[:,'reference_url'] = 'https://www.nature.com/articles/s41586-022-05547-7'
experiment.loc[:,'DOI'] = '10.1038/s41586-022-05547-7'
experiment.loc[:,'xrefs'] = 'E-MTAB-11067[ArrayExpress]'

experiment.head()

experiment.loc[:,'comment'] = 'bonobo single cell experiment from PMID 36544022'

experiment.head()

experiment.to_csv(experiment_to_add_path, sep="\t", index=False, quoting=csv.QUOTE_ALL)

library_to_add = pd.read_csv(library_to_add_path, sep='\t', index_col=False, keep_default_na=False, na_values=['NULL','null', 'nan','NaN', " "], dtype=object)
experiment_to_add = pd.read_csv(experiment_to_add_path, sep='\t', index_col=False, keep_default_na=False, na_values=['NULL','null', 'nan','NaN', " "], dtype=object)

# pull from git and pull in library/experiment file
! git pull
git_library = pd.read_csv(git_library_path, sep='\t', index_col=False, keep_default_na=False, na_values=['NULL','null', 'nan','NaN', " "], dtype=object)
git_experiment = pd.read_csv(git_experiment_path, sep='\t', index_col=False, keep_default_na=False, na_values=['NULL','null', 'nan','NaN', " "], dtype=object)

# library file
if set(library_to_add.columns) == set(git_library.columns):
    print('The columns in the library file match')
else:
    print('The columns in the library file DO NOT MATCH')

# experiment file
if set(experiment_to_add.columns) == set(git_experiment.columns):
    print('The columns in the experiment file match')
else:
    print('The columns in the experiment file DO NOT MATCH')


# maybe to make this something more like "COLUMNS GOOD - LIBRARY" and "COLUMNS BAD - EXPERIMENT"

Already up to date.
The columns in the library file match
The columns in the experiment file match

library_git_plus_new = pd.concat([git_library, library_to_add], ignore_index = True, sort = False)
old_length = git_library.shape[0]
start = old_length - 2
end = old_length + 5
view_lib = library_git_plus_new.iloc[start:end]
view_lib

experiment_git_plus_new = pd.concat([git_experiment, experiment_to_add], ignore_index = True, sort = False)
experiment_git_plus_new.tail(n=3)

# 10X only
barcode_file_for_git = pd.read_csv(barcode_to_add_path, sep='\t', index_col=False, keep_default_na=False, na_values=['NULL','null', 'nan','NaN', " "], dtype=object)
barcode_file_for_git.head(5)

! git pull

Already up to date.

library_git_plus_new.to_csv(git_library_path, sep="\t", index=False, quoting=csv.QUOTE_ALL)
update_format(git_library_path)
experiment_git_plus_new.to_csv(git_experiment_path, sep="\t", index=False, quoting=csv.QUOTE_ALL)
update_format(git_experiment_path)

# 10X only
barcode_file_for_git.to_csv(git_barcode_path, sep="\t", index=False, quoting=csv.QUOTE_ALL)
update_format(git_barcode_path)

! git status

On branch develop
Your branch is up to date with 'origin/develop'.

Changes not staged for commit:
  (use "git add <file>..." to update what will be committed)
  (use "git restore <file>..." to discard changes in working directory)
	modified:   ../../../scRNA_Seq/scRNASeqExperiment.tsv
	modified:   ../../../scRNA_Seq/scRNASeqLibrary_merged.tsv

Untracked files:
  (use "git add <file>..." to include in what will be committed)
	./
	../SRP356459/barcode_ERP132587.csv
	../../../scRNA_Seq/scRNASeq_barcode_ERP132587.tsv

no changes added to commit (use "git add" and/or "git commit -a")

# 10X (barcode file)
! git add $git_experiment_path $git_library_path $git_barcode_path

! git status

On branch develop
Your branch is up to date with 'origin/develop'.

Changes to be committed:
  (use "git restore --staged <file>..." to unstage)
	modified:   ../../../scRNA_Seq/scRNASeqExperiment.tsv
	modified:   ../../../scRNA_Seq/scRNASeqLibrary_merged.tsv
	new file:   ../../../scRNA_Seq/scRNASeq_barcode_ERP132587.tsv

Untracked files:
  (use "git add <file>..." to include in what will be committed)
	./
	../SRP356459/barcode_ERP132587.csv

! git commit -m $commit_message_exp

[develop 8ba35c4] adding annotated scRNA experiment ERP132587
 3 files changed, 9895 insertions(+), 4 deletions(-)
 create mode 100644 scRNA_Seq/scRNASeq_barcode_ERP132587.tsv

! git push

Enumerating objects: 10, done.
Counting objects: 100% (10/10), done.
Delta compression using up to 12 threads
Compressing objects: 100% (6/6), done.
Writing objects: 100% (6/6), 78.33 KiB | 5.59 MiB/s, done.
Total 6 (delta 4), reused 0 (delta 0), pack-reused 0
remote: 
remote: To create a merge request for develop, visit:
remote:   https://gitlab.sib.swiss/Bgee/expression-annotations/-/merge_requests/new?merge_request%5Bsource_branch%5D=develop
remote: 
To https://gitlab.sib.swiss/Bgee/expression-annotations.git
   dbfc973..8ba35c4  develop -> develop

! git status

! git add $path_to_output

! git commit -m $commit_message_py

! git push

	cell_type	notes_cell	cellTypeId_	cellTypeName_	cellTypeAnnotationStatus_	cell_type_new
0		should be NA/none	CL:0000255	eukaryotic cell	other	none
1	Undifferentiated_Spermatogonia		CL:0000020	spermatogonium	missing child term	Undifferentiated_Spermatogonia
2	Differentiated_Spermatogonia		CL:0000020	spermatogonium	missing child term	Differentiated_Spermatogonia
3	Early_Round_spermatids	early spermatid aka round spermatid definition: A spermatid in an early stage of maturation that has a round morphology and is transcriptionally active	CL:4030036	early spermatid	missing child term	Early_Round_spermatids
4	Elongated_spermatids	CL late spermatid definition: A spermatid in a late stage of maturation that has an elongated morphology and is transcriptionally inert when the acrosome is fully developed.	CL:4030037	late spermatid	perfect match	Elongated_spermatids
5	Late_Round_spermatids	early spermatid aka round spermatid definition: A spermatid in an early stage of maturation that has a round morphology and is transcriptionally active	CL:4030036	early spermatid	missing child term	Late_Round_spermatids
6	Leptotene_Spermatocytes	Leptotene, Zygotene, and Pachytene spermatocytes are all primary spermatocytes	CL:0000656	primary spermatocyte	missing child term	Leptotene_Spermatocytes
7	Pachytene_Spermatocytes	Leptotene, Zygotene, and Pachytene spermatocytes are all primary spermatocytes	CL:0000656	primary spermatocyte	missing child term	Pachytene_Spermatocytes
8	Zygotene_Spermatocytes	Leptotene, Zygotene, and Pachytene spermatocytes are all primary spermatocytes	CL:0000656	primary spermatocyte	missing child term	Zygotene_Spermatocytes
9	Other_somatic		CL:0000255	eukaryotic cell	other	Other_somatic
10	Sertoli	somatic cells that nurture the germ cells during spermatogenesis	CL:0000216	Sertoli cell	perfect match	Sertoli

	cell_type	notes_cell	cellTypeId_	cellTypeName_	cellTypeAnnotationStatus_	cell_type_new
0		should be NA/none	CL:0000255	eukaryotic cell	other	none
1	Undifferentiated_Spermatogonia		CL:0000020	spermatogonium	missing child term	Undifferentiated_Spermatogonia
2	Differentiated_Spermatogonia		CL:0000020	spermatogonium	missing child term	Differentiated_Spermatogonia
3	Early_Round_spermatids	early spermatid aka round spermatid definition: A spermatid in an early stage of maturation that has a round morphology and is transcriptionally active	CL:4030036	early spermatid	missing child term	Early_Round_spermatids
4	Elongated_spermatids	CL late spermatid definition: A spermatid in a late stage of maturation that has an elongated morphology and is transcriptionally inert when the acrosome is fully developed.	CL:4030037	late spermatid	perfect match	Elongated_spermatids
5	Late_Round_spermatids	early spermatid aka round spermatid definition: A spermatid in an early stage of maturation that has a round morphology and is transcriptionally active	CL:4030036	early spermatid	missing child term	Late_Round_spermatids
6	Leptotene_Spermatocytes	Leptotene, Zygotene, and Pachytene spermatocytes are all primary spermatocytes	CL:0000656	primary spermatocyte	missing child term	Leptotene_Spermatocytes
7	Pachytene_Spermatocytes	Leptotene, Zygotene, and Pachytene spermatocytes are all primary spermatocytes	CL:0000656	primary spermatocyte	missing child term	Pachytene_Spermatocytes
8	Zygotene_Spermatocytes	Leptotene, Zygotene, and Pachytene spermatocytes are all primary spermatocytes	CL:0000656	primary spermatocyte	missing child term	Zygotene_Spermatocytes
9	Other_somatic		CL:0000255	eukaryotic cell	other	Other_somatic
10	Sertoli	somatic cells that nurture the germ cells during spermatogenesis	CL:0000216	Sertoli cell	perfect match	Sertoli

	#libraryId	experimentId	platform	SRSId	anatId	anatName	stageId	stageName	url_GSM	infoOrgan	infoStage	anatAnnotationStatus	stageAnnotationStatus	sex	strain	genotype	speciesId	RNAseqTags	protocol	protocolType	lib_name	sampleName	comment	annotatorId	lastModificationDate
59069	SRX23367374	SRP485481	Illumina NovaSeq 6000	SRS20229690	UBERON:0002114	duodenum	CfamDv:0000007	postnatal stage	https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi...	Duodenum	NA	perfect match	other	NA	Beagle	Wt	9615	scRNA-seq	10X Genomics V3	3'end	h_2	SAMN39578686	PMID:38933260, Healthy dogs were selected from...	ANN	2025-01-20
59070	SRX23367373	SRP485481	Illumina NovaSeq 6000	SRS20229689	UBERON:0002114	duodenum	CfamDv:0000007	postnatal stage	https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi...	Duodenum	NA	perfect match	other	NA	Beagle	Wt	9615	scRNA-seq	10X Genomics V3	3'end	h_1	SAMN39578687	PMID:38933260, Healthy dogs were selected from...	ANN	2025-01-20
59071	ERX6700458	ERP132587	NextSeq 550	ERS8071686	UBERON:0000473	testis	PpanDv:0000025	15-year-old stage		testis	15 years	perfect match	perfect match	M			9597	Sn-scRNA-seq	10X Genomics V2	3'end	SN224	SAMEA10418842		SAC	2025-01-28
59072	ERX6700457	ERP132587	NextSeq 550	ERS8071685	UBERON:0000473	testis	PpanDv:0000040	aged stage		testis	36 years	perfect match	missing child term	M			9597	Sn-scRNA-seq	10X Genomics V2	3'end	SN219	SAMEA10418841		SAC	2025-01-28

	#experimentId	experimentName	experimentDescription	experimentSource	experimentStatus	RNAseqTags	numberOfAnnotatedLibraries	protocol	protocolType	GSE	Bioproject	PMID	reference_url	DOI	xrefs	comment
106	SRP467631	A high-resolution transcriptomic and spatial a...	The mammalian brain consists of millions to bi...	SRA	total	scRNA-seq	781	10X Genomics V2, 10X Genomics V3	3'end	GSE246717	PRJNA1030397	38092916	https://pmc.ncbi.nlm.nih.gov/articles/PMC10719...	10.1038/s41586-023-06812-z		Allen Brain Cell Atlas - mouse whole brain
107	SRP485481	Single-Cell RNA Sequencing Investigation of th...	We used single-cell RNA sequencing to characte...	SRA	partial	scRNA-seq	3	10X Genomics V3	3'end	GSE254005	PRJNA1068098	38933260	https://pmc.ncbi.nlm.nih.gov/articles/PMC11199...	10.3389/fimmu.2024.1397590		only normal libraries have been reported in ou...
108	ERP132587	snRNA-seq of bonobo (Pan paniscus) adult testis	Single-nucleus RNA sequencing (snRNA-seq) was ...	ENA	total	Sn-scRNA-seq	2	10X Genomics V2	3'end		PRJEB48245	36544022	https://www.nature.com/articles/s41586-022-055...	10.1038/s41586-022-05547-7	E-MTAB-11067[ArrayExpress]	bonobo single cell experiment from PMID 36544022

	barcode	library	experiment	tissue	cell_type	cellTypeId	cellTypeName	cellTypeAnnotationStatus	name_Library
0	TGCGTGGAGTGGGCTA	ERX6700458	ERP132587	testis	Undifferentiated_Spermatogonia	CL:0000020	spermatogonium	missing child term	SN224
1	TGTATTCCAACACCCG	ERX6700457	ERP132587	testis	Undifferentiated_Spermatogonia	CL:0000020	spermatogonium	missing child term	SN219
2	TCAATCTTCACGACTA	ERX6700457	ERP132587	testis	Undifferentiated_Spermatogonia	CL:0000020	spermatogonium	missing child term	SN219
3	CACCAGGCATCGATGT	ERX6700457	ERP132587	testis	Undifferentiated_Spermatogonia	CL:0000020	spermatogonium	missing child term	SN219
4	TAAGAGAAGCCTATGT	ERX6700457	ERP132587	testis	Undifferentiated_Spermatogonia	CL:0000020	spermatogonium	missing child term	SN219

ERP132587¶

annotation summary¶

set variables, import packages, define functions¶

script¶

library annnotations¶

anatomical entity¶

stage¶

sex, strain, genotype, speciesId¶

protocol & RNAseqTags¶

condition¶

annotator id, last modification date¶

comments¶

save complete file with correct columns¶

script - barcode (10X only)¶

check library names match¶

cell type annotation - 10X version¶

experiment annotations¶

experiment and protocol details¶

paper and xrefs¶

comments¶

save complete file¶

QA time¶

to add things here¶

check columns match¶

view files¶

add annotations to git¶

add annotation folder and script to git¶

	#libraryId	experimentId	platform	SRSId	anatId	anatName	cellTypeId	cellTypeName	stageId	stageName	url_GSM	infoOrgan	infoCellType_abInitio	infoCellType_inferred	clusterId	clusterName	infoStage	anatAnnotationStatus	cellTypeAnnotationStatus	stageAnnotationStatus	sex	strain	genotype	speciesId	RNAseqTags	protocol	protocolType	lib_name	sampleName	comment	condition	annotatorId	lastModificationDate	library_contruction_protocol	source_qc	lib_name_2	lib_name_3	source_name	individual	infoStage_2	infoStage_3
0	ERX6700458	ERP132587	NextSeq 550	ERS8071686								testis					15 years				M			9597		10X Genomics V2,10X Genomics	3'end	SN224	SAMEA10418842				28/01/2025	Tissue pieces were homogenized in prechilled 250 mM sucrose, 25 mM KCl, 5 mM MgCl2, 10 mM HEPES pH 8, 1 %, BSA, 0.1 % IGEPAL, 1 µM DTT, 0.4 U/µL RNaseIn, and 0.2 U/µL Superasin and lysed for 5 min on ice. The lysate was centrifuged at 100 x g for 1 min at 4 °C. The supernatant was transferred to a new reaction tube and centrifuged at 500 x g for 5 min at 4 °C. The supernatant was removed and the pellet resuspended in 1 mg/mL DSP in PBS and incubated for 30 min at room temperature. The fixation was quenched by addition of Tris-HCl to a final concentration of 20 mM. The fixed suspension was pelleted at 500 x g for 5 min at 4 °C. The supernatant was removed and the pellet resuspended in 250 mM sucrose, 25 mM KCl, 5 mM MgCl2, 10 mM TRIS-HCl pH 8, 1 %, BSA, 1 µM DTT, 0.4 U/µL RNaseIn, and 0.2 U/µL Superasin. This was centrifuged at 500 x g for 5 min at 4 °C. The supernatant was removed and the pellet resuspended in PBS. Nuclei were isolated through a combination of mechanical and chemical lysis. Per library 15,000 – 20,000 nuclei were loaded into one channel of the ChromiumTM Single Cell A Chip (10X Genomics®). Libraries were prepared using Chromium Single Cell 3′ Library & Gel Bead Kit v2 according to manufacturer's instructions.		E-MTAB-11067:SN224			2	adult	public
1	ERX6700457	ERP132587	NextSeq 550	ERS8071685								testis					36 years				M			9597		10X Genomics V2,10X Genomics	3'end	SN219	SAMEA10418841				28/01/2025	Tissue pieces were homogenized in prechilled 250 mM sucrose, 25 mM KCl, 5 mM MgCl2, 10 mM HEPES pH 8, 1 %, BSA, 0.1 % IGEPAL, 1 µM DTT, 0.4 U/µL RNaseIn, and 0.2 U/µL Superasin and lysed for 5 min on ice. The lysate was centrifuged at 100 x g for 1 min at 4 °C. The supernatant was transferred to a new reaction tube and centrifuged at 500 x g for 5 min at 4 °C. The supernatant was removed and the pellet resuspended in 1 mg/mL DSP in PBS and incubated for 30 min at room temperature. The fixation was quenched by addition of Tris-HCl to a final concentration of 20 mM. The fixed suspension was pelleted at 500 x g for 5 min at 4 °C. The supernatant was removed and the pellet resuspended in 250 mM sucrose, 25 mM KCl, 5 mM MgCl2, 10 mM TRIS-HCl pH 8, 1 %, BSA, 1 µM DTT, 0.4 U/µL RNaseIn, and 0.2 U/µL Superasin. This was centrifuged at 500 x g for 5 min at 4 °C. The supernatant was removed and the pellet resuspended in PBS. Nuclei were isolated through a combination of mechanical and chemical lysis. Per library 15,000 – 20,000 nuclei were loaded into one channel of the ChromiumTM Single Cell A Chip (10X Genomics®). Libraries were prepared using Chromium Single Cell 3′ Library & Gel Bead Kit v2 according to manufacturer's instructions.		E-MTAB-11067:SN219			1	adult	public